justin
0e625553e5
CORPUS — 4,299 GH plot reports added (3,797 written + 502 from the
earlier slow run + 319 sitemap-listed URLs that 404'd as
discontinued). Combined with prior 760 varieties + 14 AgriPro
trials = 5,073 total chunks now indexed.
scrape/sources/gh_plot_reports.py — concurrency speedup:
- 4 worker threads (ThreadPoolExecutor), each with its own
requests.Session for connection-pool efficiency.
- Shared class-level rate limiter (0.25 sec between ANY two
requests across all threads). Net throughput ~4 req/sec —
well below any rate-limit threshold a public site enforces.
- Diagnosis vs original 1 req/sec: GH had ZERO rate limiting,
zero 429s, zero retries. The 1 sec self-throttle was just too
conservative. Bench:
1 worker / 1.0 sec throttle: ~0.4 plots/sec (190 min ETA)
4 workers / 0.25 sec throttle: ~3 plots/sec (~25 min actual)
rag/chunk.py — chunk size cap for nomic-embed-text's 2048-token
context window:
- Empirically tested: failure threshold is ~5,250 chars on
numeric-heavy trial chunks (chars/token ratio 2.4 vs 3.5 for
prose). Cap at 4,500 chars to be safely under at worst-case
2.2 chars/token.
- Applied to BOTH variety and trial chunks. Marked truncated
chunks with metadata.embed_truncated = True; FULL text stays
in the on-disk .md for get_page to return verbatim.
.gitea/workflows/{refresh,image-only}.yml — OLLAMA_URL pool
restructured for the 4 GPU-pinned endpoints. Bench (50-chunk
batches on nomic-embed-text):
.0.125:11434 (RTX 40-series) 242 embeds/sec ← weight ×4
.0.2:11436 (GPU-pinned) 108 embeds/sec ← weight ×2
.0.2:11435 (GPU-pinned) 72 embeds/sec ← weight ×1
localhost (TITAN X) 37 embeds/sec ← weight ×1
Weighting is done by listing the URL multiple times in
OLLAMA_URL since the embedder uses round-robin. .0.2:11434 is
explicitly EXCLUDED — it isn't pinned to a specific GPU.
Combined index rebuild for 5,073 chunks now finishes in ~3 min
(was 19+ on the single-endpoint pool).
Smoke tests:
✓ list_versions: 5,073 docs across 6 sources, 2 vendors, 6
brands, 4 crops (corn 2711, soy 2016, silage 223, wheat 123).
✓ search_trials({crop=corn, state=IA, year=2024}): 3 IA 2024
corn trials surfaced.
✓ search_trials("Phytophthora resistance soybean trial"): NK
NK43-W1XFS top-1 in LA 2024 trial (cross-vendor result).
✓ search_trials("AP Iliad Idaho wheat"): AgriPro Washington/N
Idaho 2025 trial surfaced.
✓ search_trials(product=DKC65-95): 3 corn trials containing
that hybrid in IL/IA 2024.
✓ search_trials(product=NK1701): 3 corn trials in AR/MS 2024.
✓ Product filter correctly returns EMPTY for products that
aren't in the corpus (DKC65-20 is a 2023 product; 2023 plots
deferred). Anti-hallucination contract preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3.2 KiB
3.2 KiB
Soybean yield trial — Ohio, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Ohio (OH)
- Year: 2024
- Plot ID: 2419726
- Cooperator: Ohio State University - Mercer County (Late)
- Planted: 2024-05-22
- Harvested: 2024-10-09
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/oh/2024/2419726
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Seed | Consultants | SC7355E | 68.2 | - | - | $716.10 |
| 2 | Ebberts | G3690E | - | 67.9 | - | - | $712.95 |
| 3 | Seed | Genetics | Direct ET-3739E3S | 66.9 | - | - | $702.45 |
| 4 | Xitavo | XO | 3555E | 66.8 | - | - | $701.40 |
| 5 | Benson | Hill | BH35A231 | 65.2 | - | - | $684.60 |
| 5 | Xitavo | XO | 3855E | 65.2 | - | - | $684.60 |
| 7 | Blue | River | Organic Seed 39R4 | 65.1 | - | - | $683.55 |
| 8 | Seed | Consultants | SC7375E | 64.6 | - | - | $678.30 |
| 9 | Seed | Genetics | Direct ET-4738E3 | 64.5 | - | - | $677.25 |
| 10 | Seed | Consultants | SC7385E | 63.8 | - | - | $669.90 |
| 11 | Benson | Hill | N35D950S | 63.5 | - | - | $666.75 |
| 12 | Ebberts | G3580ES | - | 63.4 | - | - | $665.70 |
| 13 | Xitavo | XO | 3795E | 63.3 | - | - | $664.65 |
| 14 | Benson | Hill | BH39A232 | 63.2 | - | - | $663.60 |
| 14 | NK | NK36-Q6E3S | Enlist E3 ® STS ® | 63.2 | - | - | $663.60 |
| 16 | Benson | Hill | BH37Q218 | 63.1 | - | - | $662.55 |
| 17 | Ebberts | G3760ES | - | 62.7 | - | - | $658.35 |
| 17 | NK | NK37-C1E3 | Enlist E3 ® | 62.7 | - | - | $658.35 |
| 19 | Asgrow | AG39XF3 | - | 62.3 | - | - | $654.15 |
| 20 | Seed | Genetics | Direct ET-4739E3 | 61.8 | - | - | $648.90 |
| 21 | Benson | Hill | BX37C755 | 61.6 | - | - | $646.80 |
| 22 | Ebberts | G3880E | - | 61.5 | - | - | $645.75 |
| 23 | Axis | Seed | 3605XF | 61.4 | - | - | $644.70 |
| 24 | Seed | Genetics | Direct ET-3735E3 | 61.3 | - | - | $643.65 |
| 25 | Benson | Hill | BH35A233 | 60.9 | - | - | $639.45 |
| 26 | Seed | Consultants | SC7364E | 60.7 | - | - | $637.35 |
| 27 | Asgrow | AG36XF4 | - | 60.5 | - | - | $635.25 |
| 28 | Benson | Hill | C38H052S | 60.1 | - | - | $631.05 |
| 29 | Axis | Seed | 3514ES | 59.8 | - | - | $627.90 |
| 29 | Blue | River | Organic Seed 3418N | 59.8 | - | - | $627.90 |
| 31 | Xitavo | XO | 3655E | 59.5 | - | - | $624.75 |
| 32 | Seed | Genetics | Direct ET-4734E3S | 59.3 | - | - | $622.65 |
| 33 | NK | NK34-Z8E3S | Enlist E3 ® STS ® | 59.1 | - | - | $620.55 |
| 34 | Seed | Genetics | Direct ET-4736E3 Enlist E3 ® | 58.8 | - | - | $617.40 |
| 35 | Benson | Hill | BH37U205 | 58.4 | - | - | $613.20 |
| 36 | DonMario | Seeds | DM38E54 | 58.1 | - | - | $610.05 |
| 37 | Benson | Hill | BX36Q861 | 57.8 | - | - | $606.90 |
| 37 | Blue | River | Organic Seed 42D40 | 57.8 | - | - | $606.90 |
| 39 | DonMario | Seeds | DM36E94 | 57.4 | - | - | $602.70 |
| 40 | Benson | Hill | BX37Q467 | 57.0 | - | - | $598.50 |
| 41 | Axis | Seed | 3835E | 56.1 | - | - | $589.05 |
| 42 | Asgrow | AG43XF2 | - | 55.3 | - | - | $580.65 |
Top 5 by Yield: Consultants (Seed) 68.2, G3690E (Ebberts) 67.9, Genetics (Seed) 66.9, XO (Xitavo) 66.8, Hill (Benson) 65.2.